FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.; worldlabs-mcp: worldlabs-mcp is a Model Context Protocol gateway to World Labs' Marble and Spark 2.0 engines. It enables generation of navigable 3D worlds from diverse inputs (text, image, video, panorama), real-time streaming via Gaussian splat rendering, and spatial voice agent integration. The project includes a web dashboard, multiple export targets (Resonite, Blender, Unity), and VR headset support.
Meeting transcription with speaker labels, timestamps, and punctuation
Generate navigable 3D worlds for VR/AR experiences from text or images